Hugging Face's logo

dnth
/
setfit-riasec-classifier

Text Classification
setfit
Safetensors
sentence-transformers
mpnet
generated_from_setfit_trainer
Eval Results (legacy)
Model card Files
xet
Community
dnth commited on
Commit
0d4e73f
·
verified ·
1 Parent(s): 0fc4c84

Add SetFit model

Browse files
Files changed (13) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +0 -0
  3. config.json +23 -0
  4. config_sentence_transformers.json +14 -0
  5. config_setfit.json +125 -0
  6. model.safetensors +3 -0
  7. model_head.pkl +3 -0
  8. modules.json +14 -0
  9. sentence_bert_config.json +4 -0
  10. special_tokens_map.json +51 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +60 -0
  13. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MPNetModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "dtype": "float32",
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "mpnet",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "relative_attention_num_buckets": 32,
21
+ "transformers_version": "4.56.2",
22
+ "vocab_size": 30527
23
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "5.1.1",
4
+ "transformers": "4.56.2",
5
+ "pytorch": "2.8.0+cu128"
6
+ },
7
+ "model_type": "SentenceTransformer",
8
+ "prompts": {
9
+ "query": "",
10
+ "document": ""
11
+ },
12
+ "default_prompt_name": null,
13
+ "similarity_fn_name": "cosine"
14
+ }
config_setfit.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels": [
3
+ "RIA",
4
+ "RIS",
5
+ "RIE",
6
+ "RIC",
7
+ "RAI",
8
+ "RAS",
9
+ "RAE",
10
+ "RAC",
11
+ "RSI",
12
+ "RSA",
13
+ "RSE",
14
+ "RSC",
15
+ "REI",
16
+ "REA",
17
+ "RES",
18
+ "REC",
19
+ "RCI",
20
+ "RCA",
21
+ "RCS",
22
+ "RCE",
23
+ "IRA",
24
+ "IRS",
25
+ "IRE",
26
+ "IRC",
27
+ "IAR",
28
+ "IAS",
29
+ "IAE",
30
+ "IAC",
31
+ "ISR",
32
+ "ISA",
33
+ "ISE",
34
+ "ISC",
35
+ "IER",
36
+ "IEA",
37
+ "IES",
38
+ "IEC",
39
+ "ICR",
40
+ "ICA",
41
+ "ICS",
42
+ "ICE",
43
+ "ARI",
44
+ "ARS",
45
+ "ARE",
46
+ "ARC",
47
+ "AIR",
48
+ "AIS",
49
+ "AIE",
50
+ "AIC",
51
+ "ASR",
52
+ "ASI",
53
+ "ASE",
54
+ "ASC",
55
+ "AER",
56
+ "AEI",
57
+ "AES",
58
+ "AEC",
59
+ "ACR",
60
+ "ACI",
61
+ "ACS",
62
+ "ACE",
63
+ "SRI",
64
+ "SRA",
65
+ "SRE",
66
+ "SRC",
67
+ "SIR",
68
+ "SIA",
69
+ "SIE",
70
+ "SIC",
71
+ "SAR",
72
+ "SAI",
73
+ "SAE",
74
+ "SAC",
75
+ "SER",
76
+ "SEI",
77
+ "SEA",
78
+ "SEC",
79
+ "SCR",
80
+ "SCI",
81
+ "SCA",
82
+ "SCE",
83
+ "ERI",
84
+ "ERA",
85
+ "ERS",
86
+ "ERC",
87
+ "EIR",
88
+ "EIA",
89
+ "EIS",
90
+ "EIC",
91
+ "EAR",
92
+ "EAI",
93
+ "EAS",
94
+ "EAC",
95
+ "ESR",
96
+ "ESI",
97
+ "ESA",
98
+ "ESC",
99
+ "ECR",
100
+ "ECI",
101
+ "ECA",
102
+ "ECS",
103
+ "CRI",
104
+ "CRA",
105
+ "CRS",
106
+ "CRE",
107
+ "CIR",
108
+ "CIA",
109
+ "CIS",
110
+ "CIE",
111
+ "CAR",
112
+ "CAI",
113
+ "CAS",
114
+ "CAE",
115
+ "CSR",
116
+ "CSI",
117
+ "CSA",
118
+ "CSE",
119
+ "CER",
120
+ "CEI",
121
+ "CEA",
122
+ "CES"
123
+ ],
124
+ "normalize_embeddings": false
125
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f139ad8bacf6d4d70ef90c16405b2a0fff81099f77efed80de70d05695e034
3
+ size 437967672
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53c9fd2eb243f1ea8ae9b5ecb886dc3bce9c07d3aed89010d2f04aeb2092c75
3
+ size 740519
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "104": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "30526": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "eos_token": "</s>",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "never_split": null,
54
+ "pad_token": "<pad>",
55
+ "sep_token": "</s>",
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "MPNetTokenizer",
59
+ "unk_token": "[UNK]"
60
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff